© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65964
    Prev
    Next
    INDEX
    Explanations

    abundant grapes

    np_acts-logits-general · gemini-2.5-flash-lite

    becomes to, based on, recognizes, chuckled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     വാങ്ങ
    0.55
     sprzedaży
    0.50
     ս
    0.49
    traf
    0.48
     sprzed
    0.48
     vattati
    0.48
     형태
    0.46
    求める
    0.46
     devad
    0.46
     त्याची
    0.45
    POSITIVE LOGITS
     "
    0.48
     '
    0.47
     Ames
    0.46
    c
    0.45
     amas
    0.44
    具有
    0.42
    эння
    0.42
    '$\
    0.41
     منصور
    0.41
     Advent
    0.41
    Activations Density 0.000%

    No Known Activations